This paper addresses the design of a model-based 3D
object pose estimation algorithm, which is one of the major
techniques to develop a robust robotic vision system using a
monocular camera. The proposed system first extracts line
features of a captured image by using edge detection and
Hough transform techniques. Given a CAD model of the
object-of-interest, the 6-DOF pose of the object can then be
estimated via a novel edge-based nonlinear model fitting
algorithm, which is a nonlinear optimization process for
estimating the optimal object pose based on an edge-based
distance metric. Experimental results validate the
performance of the proposed system.
關聯:
Proceedings of the 3rd IIAE International Conference on Intelligent Systems and Image Processing 2015, pp.59-62